A method and system for detecting the post-construction state of a pipe jacking

Abstract

The application provides a pipe jacking post-operation state detection method and system, the method comprises the following steps: data preprocessing is performed on pipe jacking post-operation state detection data to obtain processed data; key influence factors are determined, and key data sets are extracted from the processed data based on the key influence factors; data in the key data sets is subjected to combined denoising processing to obtain denoised data sets; the denoised data sets are subjected to clustering processing by using an improved clustering algorithm to obtain clustered data sets; each key influence factor is subjected to combined weighting to obtain an influence weight, and the final pipe jacking post-operation state is determined based on the influence weight and the clustered data sets. The application can effectively extract effective data from mixed data and remove white noise, colored noise and the like in the data, can greatly improve the clustering speed and reduce the feature dimension, so as to improve the quality and effectiveness of the data and finally improve the accuracy and effectiveness of the safety state recognition.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of top pipe state detection, and particularly relates to a top pipe post-construction state detection method and system. BACKGROUND

[0002] Top pipe construction is a trenchless construction method, which is a pipe burying construction technology without or with less excavation. The top pipe construction is to overcome the friction between the pipe and the surrounding soil by means of the jacking force generated by the jacking equipment in the working pit, and to jacking the pipe into the soil according to the designed slope, and to transport the earthwork away. After one section of pipe is jacked into the soil layer, the second section of pipe is lowered to continue jacking. The principle is to use the thrust force between the main jacking cylinder and the pipe and the relay to push the tool pipe or the tunneling machine from the working pit through the soil layer to the receiving pit. The pipe is buried between the two pits after the tool pipe or the tunneling machine.

[0003] In order to ensure safety, it is usually necessary to install a plurality of sensors around the pipe and on the pipe, and to detect the top pipe post-construction state detection data in real time through the sensors. The purpose of the detection is usually to ensure the safety of the pipe. Under the influence of the external environment (external pressure, soil environment, weather), the pipe is prone to deformation, cracking and leakage, and material degradation. In the prior art, the top pipe post-construction detection data is obtained, and safety classification is performed according to the detection data. However, in actual situations, there is a lot of noise in the detection data and some data that has little effect on the state of the top pipe. If safety classification is directly performed according to the detection data, the safety classification may be inaccurate, and there may be a great safety hazard. SUMMARY

[0004] In order to solve the above technical problems, the application provides a top pipe post-construction state detection method and system to solve the technical problems in the prior art.

[0005] In one aspect, the application provides the following technical scheme, a top pipe post-construction state detection method, comprising:

[0006] obtaining top pipe post-construction state detection data, and performing data preprocessing on the top pipe post-construction state detection data to obtain processed data;

[0007] determining key influence factors by using an analytic hierarchy process, and extracting a key data set from the processed data based on the key influence factors;

[0008] performing combined denoising processing on the data in the key data set to obtain a denoised data set;

[0009] performing clustering processing on the denoised data set by using an improved clustering algorithm to obtain a clustered data set;

[0010] Each of the key influencing factors is combined and weighted to obtain an influence weight, and the final post-construction state of the pipe jacking is determined based on the influence weight and the clustered dataset.

[0011] Compared with existing technologies, the beneficial effects of this invention are as follows: First, this invention acquires post-construction status detection data for pipe jacking, performs data preprocessing on the data to obtain processed data; then, it uses the analytic hierarchy process (AHP) to determine key influencing factors, and extracts key datasets from the processed data based on these factors; next, it performs combined denoising processing on the data in the key datasets to obtain denoised datasets; then, it uses an improved clustering algorithm to cluster the denoised datasets to obtain clustered datasets; finally, it assigns combined weights to each key influencing factor to obtain influence weights, and determines the final post-construction status of the pipe jacking based on the influence weights and the clustered datasets. This invention performs combined denoising on the data, effectively extracting valid data from mixed data and removing white noise, colored noise, etc. The subsequent clustering processing significantly improves clustering speed and reduces feature dimensions, thereby improving data quality and effectiveness. Finally, the final post-construction status of the pipe jacking is determined through influence weights, improving the accuracy and effectiveness of safety status identification.

[0012] Preferably, the step of performing combined denoising processing on the data in the key dataset to obtain a denoised dataset includes:

[0013] The data in the key dataset is decomposed to obtain several IMF components and trend terms. The several IMF components are then sorted in descending order to obtain the first IMF component set.

[0014] Calculate the noise judgment value for each IMF component in the first IMF component set. :

[0015] ;

[0016] In the formula, This indicates the number of IMF components in the first IMF component set. Indicates the first IMF component set One IMF component;

[0017] Determine the noise judgment value The target arrangement position of the IMF component corresponding to the minimum value is determined, and the IMF components before the target arrangement position are stored in the second IMF component set. The number of zero crossings of all IMF components in the first IMF component set is determined, and the IMF components with a number of zero crossings less than a preset number are stored in the third IMF component set. The remaining IMF components in the first IMF component set other than the second IMF component set and the third IMF component set are stored in the fourth IMF component set.

[0018] The second IMF component set and the third IMF component set are subjected to denoising and power transformation processes respectively to obtain the first denoised IMF component set and the second denoised IMF component set. The denoised dataset is determined based on the first denoised IMF component set and the second denoised IMF component set.

[0019] Preferably, the step of performing denoising and power transformation processing on the second IMF component set and the third IMF component set respectively to obtain a first denoised IMF component set and a second denoised IMF component set, and determining the denoised dataset based on the first denoised IMF component set and the second denoised IMF component set includes:

[0020] Wavelet threshold denoising is performed on the second IMF component set to obtain the first denoised IMF component set;

[0021] Determine the power spectrum of the third IMF component set, and determine the power spectrum matrix based on the power spectrum;

[0022] The power spectral matrix is ​​standardized to obtain a standard matrix. The eigenvectors of the standard matrix are extracted, and the principal component sequence is determined based on the eigenvectors and the standard matrix. :

[0023] ;

[0024] In the formula, For a standard matrix, For feature vectors;

[0025] The principal components in the principal component sequence are sorted in descending order of contribution, and the first few principal components after descending order are extracted to obtain the target principal components. The reconstructed power spectrum is then determined based on the target principal components. :

[0026] ;

[0027] ;

[0028] In the formula, Indicates the first One target principal component, express The corresponding feature vector, This represents the intermediate reconstructed power spectrum. They represent The Middle Line number Column elements, To reconstruct the adjustment factor, The power spectrum matrix is ​​the first... The mean of the column elements;

[0029] For the reconstructed power spectrum Phase addition and inverse Fourier transform are performed to obtain the second denoised IMF component set. :

[0030]

[0031] ;

[0032] In the formula, Represents the second denoised IMF component set The Middle One IMF component, This is the inverse Fourier transform. It is an imaginary number. Indicates the corresponding frequency phase;

[0033] The first denoised IMF component set, the second denoised IMF component set, the fourth IMF component set, and the trend term are reconstructed to obtain a denoised dataset.

[0034] Preferably, the step of using an improved clustering algorithm to cluster the denoised dataset to obtain a clustered dataset includes:

[0035] Determine the intermediate data points in the denoised dataset, and perform clustering using the intermediate data points as cluster centers to obtain the first cluster.

[0036] If the number of data in the first cluster is less than the preset number, then the positive data in the denoised dataset is stored in the positive sample dataset and the negative data is stored in the negative sample dataset.

[0037] Determine the first mean in the positive sample dataset and the second mean in the negative sample dataset, and calculate the absolute value of the difference between the first mean and the second mean;

[0038] Clustering is performed based on the absolute value of the difference, and the clustered dataset is output.

[0039] Preferably, the step of clustering based on the absolute value of the difference and outputting the clustered dataset includes:

[0040] If the absolute value of the difference is less than a preset value, then the data corresponding to the first mean or the second mean is used as the cluster center to perform clustering to obtain a second cluster.

[0041] If the number of data points in the second cluster is less than a preset number, then any point is selected in the denoised dataset as a reference point. The data range is determined with the reference point as the center and a preset distance as the radius. If the number of data points within the data range is greater than a preset density threshold, then the reference point is used as a sample point. The center of the sample point is determined and clustering is performed with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised dataset is calculated. Data points with an Euclidean distance less than a preset distance are assigned to the class corresponding to the sample point to obtain the clustered dataset.

[0042] If the absolute value of the difference is not less than a preset value, then the data corresponding to the first mean and the second mean are used as cluster centers to perform clustering to obtain the third cluster and the fourth cluster.

[0043] If the number of data points in the third cluster is less than a preset number and the number of data points in the fourth cluster is less than a preset number, then any point in the denoised dataset is randomly selected as a reference point. The data range is determined with the reference point as the center and a preset distance as the radius. If the number of data points within the data range is greater than a preset density threshold, then the reference point is used as a sample point. The center of the sample point is determined and clustered with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised dataset is calculated. Data points with an Euclidean distance less than a preset distance are assigned to the class corresponding to the sample point to obtain the clustered dataset.

[0044] Preferably, the step of combining and weighting each of the key influencing factors to obtain influence weights, and determining the final post-construction state of the pipe jacking based on the influence weights and the clustered dataset includes:

[0045] Select the least influential factor from the key influencing factors and calculate the least influential factor. First level of impact and other key influencing factors Second degree of influence :

[0046] ;

[0047] ;

[0048] In the formula, For the evaluation section, For the first The key influencing factors are in the first The index values ​​in each evaluation segment The lowest impact factor in the first The index values ​​in each evaluation segment;

[0049] Based on the first degree of influence and the second degree of influence Calculate the first weight :

[0050] ; ;

[0051] In the formula, Important values ​​for the indicator;

[0052] Construct an original evaluation matrix, and determine the weight values ​​of the indicators based on the original evaluation matrix. :

[0053] ;

[0054] In the formula, The first in the original evaluation matrix Line number Column elements;

[0055] Based on the weight value of the aforementioned indicators Determine the second weight :

[0056] ;

[0057] The first weight and the second weight are initially combined to obtain the combined weight. :

[0058] ;

[0059] In the formula, These represent the first and second combination parameters, respectively. These represent the weight sets composed of the first weight and the second weight, respectively;

[0060] Determine the objective function:

[0061] ;

[0062] The objective function is solved to obtain the updated first combined parameters. Update the second combination parameters ;

[0063] Based on the updated first combination parameters The updated second combination parameters Determine the influence weights :

[0064] ;

[0065] Construct an initial indicator evaluation matrix, and based on the initial indicator evaluation matrix and the influence weights Determine the final post-construction status of the pipe jacking project.

[0066] Preferably, the initial indicator evaluation matrix is ​​constructed based on the initial indicator evaluation matrix and the influence weights. The steps to determine the final post-construction state of the pipe jacking project include:

[0067] Determine the security classification levels and the classification criteria for each security classification level, and determine a classification matrix based on the security classification levels and the classification criteria. ,in, The number of safety classification levels;

[0068] Constructing the initial indicator evaluation matrix In the hierarchical matrix Extract the first The row vectors corresponding to the key influencing factors, if the elements in the row vectors are in a decreasing order, then when hour, ,when hour, ,when hour, If the elements in the row vector are in an increasing order, then when hour, ,when hour, ,when hour, ,in, For the clustering dataset, the first The key influencing factors are in the first Data values ​​in each evaluation segment The first index in the initial index evaluation matrix Line number Column elements, The first in the hierarchical matrix Line number Column elements;

[0069] Based on the influence weight With the initial index evaluation matrix Determine the final matrix :

[0070] ;

[0071] In the formula, For the final matrix, the first... Line number Column elements, Indicates the first The influence weights of each key influencing factor;

[0072] Based on the final matrix, the safety status evaluation function is determined. If the installation status evaluation function is satisfied, then the final post-pipe jacking status is the [number missing]. There are several safety classification levels, where the safety status evaluation function is:

[0073] ;

[0074] In the formula, Represents the nth element in the final matrix row vectors. The evaluation threshold is used.

[0075] Secondly, the present invention provides the following technical solution: a post-construction condition detection system for pipe jacking, the system comprising:

[0076] The preprocessing module is used to acquire post-construction status detection data of pipe jacking and to preprocess the post-construction status detection data of pipe jacking to obtain processed data.

[0077] An extraction module is used to identify key influencing factors using the analytic hierarchy process, and to extract a key dataset from the processed data based on the key influencing factors.

[0078] The denoising module is used to perform combined denoising processing on the data in the key dataset to obtain a denoised dataset;

[0079] The clustering module is used to perform clustering processing on the denoised dataset using an improved clustering algorithm to obtain a clustered dataset;

[0080] The status module is used to combine and assign weights to each of the key influencing factors to obtain influence weights, and to determine the final post-construction status of the pipe jacking based on the influence weights and the clustered dataset.

[0081] Thirdly, the present invention provides the following technical solution: a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the post-construction status detection method for pipe jacking as described above.

[0082] Fourthly, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the post-construction status detection method for pipe jacking as described above. Attached Figure Description

[0083] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0084] Figure 1 This is a flowchart of the post-construction status detection method for pipe jacking provided in Embodiment 1 of the present invention;

[0085] Figure 2 This is a structural block diagram of the post-construction status detection system for pipe jacking provided in Embodiment 2 of the present invention;

[0086] Figure 3 This is a schematic diagram of the hardware structure of a computer provided for another embodiment of the present invention.

[0087] The embodiments of the present invention will be further described below with reference to the accompanying drawings. Detailed Implementation

[0088] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain embodiments of the present invention, and should not be construed as limiting the present invention.

[0089] Example 1

[0090] In Embodiment 1 of the present invention, as Figure 1 As shown, a method for post-construction condition inspection of pipe jacking includes:

[0091] S1. Obtain post-construction status detection data of pipe jacking, and perform data preprocessing on the post-construction status detection data of pipe jacking to obtain processed data;

[0092] Specifically, the post-construction status detection data of the pipe jacking can be obtained by several sensors installed at corresponding locations, and the preprocessing process here is a commonly used processing method in existing technology, such as data normalization, standardization, smoothing, etc.

[0093] S2. Use the analytic hierarchy process to identify key influencing factors, and extract key datasets from the processed data based on the key influencing factors;

[0094] Specifically, the analytic hierarchy process (AHP) used here is a commonly used method in existing technologies, so it will not be elaborated on here. The AHP can identify several key influencing factors that have a high degree of impact on the post-construction state of pipe jacking. Then, based on the extracted key influencing factors, the corresponding data can be extracted from the original processed data to obtain the key dataset.

[0095] S3. Perform combined denoising processing on the data in the key dataset to obtain a denoised dataset;

[0096] Step S3 includes:

[0097] S31. Decompose the data in the key dataset to obtain several IMF components and trend terms, and sort the several IMF components in descending order to obtain the first IMF component set.

[0098] Specifically, the decomposition algorithm used here is the CEEMD algorithm. Then, the components are sorted in descending order according to their frequency to obtain the first IMF component set.

[0099] S32. Calculate the noise judgment value of each IMF component in the first IMF component set. :

[0100] ;

[0101] In the formula, This indicates the number of IMF components in the first IMF component set. Indicates the first IMF component set One IMF component.

[0102] S33. Determine the noise judgment value The target arrangement position of the IMF component corresponding to the minimum value is determined, and the IMF components before the target arrangement position are stored in the second IMF component set. The number of zero crossings of all IMF components in the first IMF component set is determined, and the IMF components with a number of zero crossings less than a preset number are stored in the third IMF component set. The remaining IMF components in the first IMF component set other than the second IMF component set and the third IMF component set are stored in the fourth IMF component set.

[0103] Specifically, noise judgment value The minimum value of the IMF component corresponds to the boundary point between the high-frequency component and the effective component. The high-frequency component, i.e., the second IMF component set, can be extracted through this boundary point. Since white noise usually exists in the high-frequency component, the high-frequency component needs to be denoised. As for the number of zero crossings, since the high-frequency component fluctuates greatly, the effective component fluctuates moderately, and the low-frequency component fluctuates little, the low-frequency component can be extracted by setting a preset number of zero crossings, i.e., the third IMF component set. Since colored noise usually exists in the low-frequency component, the low-frequency component needs to be processed accordingly. For the first IMF component set, the noisy component has been extracted separately, and the remaining components are noisy or have very little noise. They can be directly used as effective components without processing and can directly participate in the subsequent reconstruction process.

[0104] S34. Denoising and power transformation are performed on the second IMF component set and the third IMF component set respectively to obtain the first denoised IMF component set and the second denoised IMF component set. Based on the first denoised IMF component set and the second denoised IMF component set, a denoised dataset is determined.

[0105] Step S34 includes:

[0106] S341. Perform wavelet threshold denoising on the second IMF component set to obtain the first denoised IMF component set.

[0107] Specifically, wavelet thresholding denoising is a commonly used method in existing technologies, so it will not be elaborated further.

[0108] S342. Determine the power spectrum of the third IMF component set, and determine the power spectrum matrix based on the power spectrum.

[0109] S343. Standardize the power spectrum matrix to obtain a standard matrix, extract the eigenvectors of the standard matrix, and determine the principal component sequence based on the eigenvectors and the standard matrix. :

[0110] ;

[0111] In the formula, For a standard matrix, For feature vectors;

[0112] Specifically, the purpose of standardization here is to prevent a power spectrum with an excessively large value from becoming the dominant component in subsequent principal component analysis, thereby ignoring other principal components. Furthermore, the eigenvectors corresponding to the eigenvalues ​​can be obtained by calculating the eigenvalues.

[0113] S344. Sort the principal components in the principal component sequence in descending order of contribution, and extract the first few principal components after descending order to obtain the target principal components. Determine the reconstructed power spectrum based on the target principal components. :

[0114] ;

[0115] ;

[0116] In the formula, Indicates the first One target principal component, express The corresponding feature vector, This represents the intermediate reconstructed power spectrum. They represent The Middle Line number Column elements, To reconstruct the adjustment factor, The power spectrum matrix is ​​the first... The mean of the column elements;

[0117] Specifically, the contribution here refers to the proportion of a single principal component in the entire principal component sequence. Principal components with small proportions, i.e., low contributions, need to be removed. The specific reconstruction adjustment factor here is... The standard deviation of each element in the matrix, and in the above formula, after determining the intermediate reconstructed power spectrum, it needs to be inversely normalized.

[0118] S345, regarding the reconstructed power spectrum Phase addition and inverse Fourier transform are performed to obtain the second denoised IMF component set. :

[0119]

[0120] ;

[0121] In the formula, Represents the second denoised IMF component set The Middle One IMF component, This is the inverse Fourier transform. It is an imaginary number. Indicates the corresponding frequency phase;

[0122] Specifically, after the above steps, the noise in the second IMF component set and the third IMF component set can be removed, and then they can be reconstructed with the fourth IMF component set and the trend term.

[0123] S346. Reconstruct the first denoised IMF component set, the second denoised IMF component set, the fourth IMF component set, and the trend term to obtain a denoised dataset.

[0124] S4. Use an improved clustering algorithm to cluster the denoised dataset to obtain a clustered dataset;

[0125] Step S4 includes:

[0126] S41. Determine the intermediate data points in the denoised dataset, and perform clustering using the intermediate data points as cluster centers to obtain the first cluster.

[0127] Specifically, the intermediate data point here refers to the data point corresponding to the median in the denoised dataset, and the clustering here uses the clustering method described in S442 and S444 below.

[0128] S42. If the number of data in the first cluster is less than a preset number, then the positive data in the denoised dataset is stored in the positive sample dataset and the negative data is stored in the negative sample dataset.

[0129] Specifically, if the number of data in the first cluster is not less than the preset number, the data in the first cluster can be directly used as the cluster dataset.

[0130] S43. Determine the first mean in the positive sample dataset and the second mean in the negative sample dataset, and calculate the absolute value of the difference between the first mean and the second mean.

[0131] S44. Perform clustering based on the absolute value of the difference and output the clustered dataset;

[0132] Step S44 includes:

[0133] S441. If the absolute value of the difference is less than a preset value, then the data corresponding to the first mean or the second mean is used as the cluster center to perform clustering to obtain a second cluster.

[0134] S442. If the number of data points in the second cluster is less than a preset number, then any point is selected in the denoised dataset as a reference point. The data range is determined with the reference point as the center and a preset distance as the radius. If the number of data points within the data range is greater than a preset density threshold, then the reference point is used as a sample point. The center of the sample point is determined and clustering is performed with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised dataset is calculated. Data points with an Euclidean distance less than a preset distance are assigned to the class corresponding to the sample point to obtain the clustered dataset.

[0135] Specifically, if the number of data in the second cluster is not less than the preset number, the data in the second cluster can be directly used as the cluster dataset.

[0136] S443. If the absolute value of the difference is not less than a preset value, then clustering is performed using the data corresponding to the first mean and the second mean as cluster centers to obtain the third cluster and the fourth cluster.

[0137] S444. If the number of data points in the third cluster is less than a preset number and the number of data points in the fourth cluster is less than a preset number, then any point in the denoised dataset is selected as a reference point. The data range is determined with the reference point as the center and a preset distance as the radius. If the number of data points within the data range is greater than a preset density threshold, then the reference point is used as a sample point. The center of the sample point is determined and clustering is performed with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised dataset is calculated. Data points with an Euclidean distance less than a preset distance are assigned to the class corresponding to the sample point to obtain the clustered dataset.

[0138] Specifically, if the number of data in the third cluster is not less than a preset number or the number of data in the fourth cluster is not less than a preset number, then the data in the third cluster and the fourth cluster can be directly used as the cluster dataset.

[0139] Meanwhile, by taking the above steps, determining the data size in the clusters and selecting different cluster centers, the number of times sample points need to be determined can be greatly reduced, and the time complexity of clustering can also be significantly reduced, thus improving the clustering effect. This method is suitable for clustering large sample data.

[0140] S5. Combine and assign weights to each of the key influencing factors to obtain influence weights, and determine the final post-construction state of the pipe jacking based on the influence weights and the clustered dataset.

[0141] Step S5 includes:

[0142] S51. Select the least influential factor from the key influencing factors and calculate the least influential factor. First level of impact and other key influencing factors Second degree of influence :

[0143] ;

[0144] ;

[0145] In the formula, For the evaluation section, For the first The key influencing factors are in the first The index values ​​in each evaluation segment The lowest impact factor in the first The index values ​​in each evaluation segment;

[0146] Specifically, the minimum influencing factor here is determined by experts using their experience and knowledge to select the factor with the least impact. The evaluation segment here refers to the category of the post-construction state of the pipe jacking, such as leakage, cracking, deformation, etc., and the index value here can be obtained based on expert evaluation.

[0147] S52, Based on the first degree of influence and the second degree of influence Calculate the first weight :

[0148] ; ;

[0149] In the formula, This is the important value of the indicator.

[0150] S53. Construct the original evaluation matrix and determine the index weight values ​​based on the original evaluation matrix. :

[0151] ;

[0152] In the formula, The first in the original evaluation matrix Line number Column elements;

[0153] Specifically, the original evaluation matrix here can be obtained through a questionnaire scoring method.

[0154] S54, Based on the weighting value of the aforementioned indicator Determine the second weight :

[0155] .

[0156] S55. The first weight and the second weight are initially combined to obtain the combined weight. :

[0157] ;

[0158] In the formula, These represent the first and second combination parameters, respectively. These represent the weight sets composed of the first weight and the second weight, respectively;

[0159] Specifically, the combined parameters here are variables.

[0160] S56. Determine the objective function:

[0161] .

[0162] S57. Solve the objective function to obtain the updated first combined parameters. Update the second combination parameters ;

[0163] Specifically, the solution here can be obtained by differentiating the objective function, determining the system of linear differential equations that provide the conditions for the first derivative of the optimization, and then solving the system of equations.

[0164] S58. Based on the updated first combination parameters The updated second combination parameters Determine the influence weights :

[0165] ;

[0166] Specifically, after obtaining the updated first combination of parameters Update the second combination parameters Next, in order to achieve a balanced weight, the parameters need to be normalized to improve the rationality of the weight.

[0167] S59. Construct an initial indicator evaluation matrix, and based on the initial indicator evaluation matrix and the influence weights... Determine the final post-construction status of the pipe jacking project.

[0168] Step S59 includes:

[0169] S591. Determine the security classification level and the classification criteria for each security classification level, and determine the classification matrix based on the security classification level and the classification criteria. ,in, The number of safety classification levels;

[0170] Specifically, in the actual grading process, it can be divided into 5 levels, namely, very safe, safe, basically safe, less safe, and unsafe. The corresponding states are no damage, slight damage, general damage, relatively serious damage, and serious damage. By determining the grading criteria for each safety level, the corresponding grading criteria matrix can be obtained.

[0171] S592. Constructing the initial indicator evaluation matrix In the hierarchical matrix Extract the first The row vectors corresponding to the key influencing factors, if the elements in the row vectors are in a decreasing order, then when hour, ,when hour, ,when hour, If the elements in the row vector are in an increasing order, then when hour, ,when hour, ,when hour, ,in, For the clustering dataset, the first The key influencing factors are in the first Data values ​​in each evaluation segment The first index in the initial index evaluation matrix Line number Column elements, The first in the hierarchical matrix Line number Column elements;

[0172] Specifically, by determining the increasing or decreasing relationship of the row elements, it can be determined whether the corresponding grading index is better the larger it is or the smaller it is. This allows for the determination of the values ​​of the elements in the initial index evaluation matrix. hour, Assuming s is 2, then when hour, The remaining elements are 0, when hour, Assuming s is 2, then when hour, The remaining elements are 0. Similarly, the remaining elements can be obtained in the same way, i.e., based on... The value of is between two adjacent elements in the row vector, thus determining the value of the element in the initial index evaluation matrix at the corresponding position.

[0173] S593, Based on the aforementioned influence weights With the initial index evaluation matrix Determine the final matrix :

[0174] ;

[0175] In the formula, For the final matrix, the first... Line number Column elements, Indicates the first The influence weights of each key influencing factor.

[0176] S594. Based on the final matrix, determine the safety status evaluation function. If the installation status evaluation function is satisfied, then the final post-pipe jacking status is the [missing information]. There are several safety classification levels, where the safety status evaluation function is:

[0177] ;

[0178] In the formula, Represents the nth element in the final matrix row vectors. For evaluation thresholds;

[0179] Specifically, the evaluation threshold here is 0.5.

[0180] The post-construction status detection method for pipe jacking provided in Embodiment 1 of this invention first acquires post-construction status detection data and preprocesses it to obtain processed data. Then, it uses the analytic hierarchy process (AHP) to determine key influencing factors and extracts a key dataset from the processed data based on these factors. Next, it performs combined denoising processing on the data in the key dataset to obtain a denoised dataset. Then, it uses an improved clustering algorithm to cluster the denoised dataset to obtain a clustered dataset. Finally, it assigns combined weights to each key influencing factor to obtain influence weights. Based on the influence weights and the clustered dataset, it determines the final post-construction status of the pipe jacking. This invention performs combined denoising, effectively extracting valid data from mixed data and removing white noise, colored noise, etc. The subsequent clustering process significantly improves clustering speed and reduces feature dimensions, thereby improving data quality and effectiveness. Finally, the final post-construction status of the pipe jacking is determined through influence weights, improving the accuracy and effectiveness of safety status identification.

[0181] Example 2

[0182] like Figure 2 As shown, in Embodiment 2 of the present invention, a post-construction status detection system for pipe jacking is provided, the system comprising:

[0183] Preprocessing module 1 is used to acquire post-construction status detection data of pipe jacking and to preprocess the post-construction status detection data of pipe jacking to obtain processed data;

[0184] Extraction module 2 is used to determine key influencing factors using the analytic hierarchy process (AHP), and to extract key datasets from the processed data based on the key influencing factors.

[0185] The denoising module 3 is used to perform combined denoising processing on the data in the key dataset to obtain a denoised dataset;

[0186] Clustering module 4 is used to perform clustering processing on the denoised dataset using an improved clustering algorithm to obtain a clustered dataset;

[0187] The status module 5 is used to combine and assign weights to each of the key influencing factors to obtain influence weights, and to determine the final post-construction status of the pipe jacking based on the influence weights and the clustered dataset.

[0188] The noise reduction module 3 includes:

[0189] The decomposition submodule is used to decompose the data in the key dataset to obtain several IMF components and trend terms, and to sort the several IMF components in descending order to obtain the first IMF component set.

[0190] The noise submodule is used to calculate the noise judgment value for each IMF component in the first IMF component set. :

[0191] ;

[0192] In the formula, This indicates the number of IMF components in the first IMF component set. Indicates the first IMF component set One IMF component;

[0193] The permutation submodule is used to determine the noise judgment value. The target arrangement position of the IMF component corresponding to the minimum value is determined, and the IMF components before the target arrangement position are stored in the second IMF component set. The number of zero crossings of all IMF components in the first IMF component set is determined, and the IMF components with a number of zero crossings less than a preset number are stored in the third IMF component set. The remaining IMF components in the first IMF component set other than the second IMF component set and the third IMF component set are stored in the fourth IMF component set.

[0194] The denoising submodule is used to perform denoising and power transformation processing on the second IMF component set and the third IMF component set respectively to obtain the first denoised IMF component set and the second denoised IMF component set, and to determine the denoised dataset based on the first denoised IMF component set and the second denoised IMF component set.

[0195] The noise reduction submodule includes:

[0196] A denoising unit is used to perform wavelet threshold denoising processing on the second IMF component set to obtain a first denoised IMF component set.

[0197] A power spectrum unit is used to determine the power spectrum of the third IMF component set and to determine the power spectrum matrix based on the power spectrum.

[0198] A normalization unit is used to normalize the power spectrum matrix to obtain a standard matrix, extract the eigenvectors of the standard matrix, and determine the principal component sequence based on the eigenvectors and the standard matrix. :

[0199] ;

[0200] In the formula, For a standard matrix, For feature vectors;

[0201] Principal component units are used to sort the principal components in the principal component sequence in descending order of contribution, and extract the first few principal components after descending order to obtain the target principal components. The reconstructed power spectrum is then determined based on the target principal components. :

[0202] ;

[0203] ;

[0204] In the formula, Indicates the first One target principal component, express The corresponding feature vector, This represents the intermediate reconstructed power spectrum. They represent The Middle Line number Column elements, To reconstruct the adjustment factor, The power spectrum matrix is ​​the first... The mean of the column elements;

[0205] Phase unit, used for the reconstructed power spectrum Phase addition and inverse Fourier transform are performed to obtain the second denoised IMF component set. :

[0206]

[0207] ;

[0208] In the formula, Represents the second denoised IMF component set The Middle One IMF component, This is the inverse Fourier transform. It is an imaginary number. Indicates the corresponding frequency phase;

[0209] The reconstruction unit is used to reconstruct the first denoised IMF component set, the second denoised IMF component set, the fourth IMF component set, and the trend term to obtain a denoised dataset.

[0210] The clustering module 4 includes:

[0211] The first clustering submodule is used to determine the intermediate data points in the denoised dataset, and to perform clustering with the intermediate data points as cluster centers to obtain the first cluster.

[0212] The data partitioning submodule is used to store positive data in the denoised dataset into the positive sample dataset and negative data into the negative sample dataset if the number of data in the first cluster is less than a preset number.

[0213] The absolute value submodule is used to determine the first mean in the positive sample dataset and the second mean in the negative sample dataset, and to calculate the absolute value of the difference between the first mean and the second mean;

[0214] The second clustering submodule is used to perform clustering based on the absolute value of the difference and output the clustered dataset.

[0215] The second clustering submodule includes:

[0216] The first clustering unit is used to cluster data with the first mean or the second mean as the cluster center if the absolute value of the difference is less than a preset value, so as to obtain a second cluster.

[0217] The second clustering unit is used to: if the number of data points in the second cluster is less than a preset number, then arbitrarily select a point in the denoised dataset as a reference point, determine the data range with the reference point as the center and a preset distance as the radius; if the number of data points within the data range is greater than a preset density threshold, then take the reference point as a sample point, determine the center of the sample point, and use the center of the sample point as the cluster center for clustering; calculate the Euclidean distance between the sample point and the remaining data points in the denoised dataset; and assign data points with an Euclidean distance less than a preset distance to the class corresponding to the sample point to obtain the clustered dataset.

[0218] The third clustering unit is used to cluster the data corresponding to the first mean and the second mean respectively as cluster centers if the absolute value of the difference is not less than a preset value, so as to obtain the third cluster and the fourth cluster.

[0219] The fourth clustering unit is used to: if the number of data points in the third cluster is less than a preset number and the number of data points in the fourth cluster is less than a preset number, then arbitrarily select a point in the denoised dataset as a reference point, determine a data range with the reference point as the center and a preset distance as the radius, and if the number of data points within the data range is greater than a preset density threshold, then take the reference point as a sample point, determine the center of the sample point, and use the center of the sample point as the cluster center for clustering, calculate the Euclidean distance between the sample point and the remaining data points in the denoised dataset, and assign data points with an Euclidean distance less than a preset distance to the class corresponding to the sample point to obtain the clustered dataset.

[0220] The status module 5 includes:

[0221] The influence degree submodule is used to select the lowest influence factor among the key influence factors and calculate the lowest influence factor. First level of impact and other key influencing factors Second degree of influence :

[0222] ;

[0223] ;

[0224] In the formula, For the evaluation section, For the first The key influencing factors are in the first The index values ​​in each evaluation segment The lowest impact factor in the first The index values ​​in each evaluation segment;

[0225] The first weighting submodule is used to base the weighting on the first degree of influence. and the second degree of influence Calculate the first weight :

[0226] ; ;

[0227] In the formula, Important values ​​for the indicator;

[0228] The proportion submodule is used to construct the original evaluation matrix and determine the proportion values ​​of the indicators based on the original evaluation matrix. :

[0229] ;

[0230] In the formula, The first in the original evaluation matrix Line number Column elements;

[0231] The second weighting submodule is used to base the weighting value of the indicator. Determine the second weight :

[0232] ;

[0233] The combination submodule is used to initially combine the first weight and the second weight to obtain the combined weight. :

[0234] ;

[0235] In the formula, These represent the first and second combination parameters, respectively. These represent the weight sets composed of the first weight and the second weight, respectively;

[0236] The function submodule is used to determine the target function:

[0237] ;

[0238] The solver submodule is used to solve the objective function to obtain updated first combined parameters. Update the second combination parameters ;

[0239] The influence weight submodule is used to update the first combination parameters based on the above. The updated second combination parameters Determine the influence weights :

[0240] ;

[0241] The status output submodule is used to construct an initial indicator evaluation matrix, based on the initial indicator evaluation matrix and the influence weights. Determine the final post-construction status of the pipe jacking project.

[0242] The status output submodule includes:

[0243] A grading unit is used to determine security grading levels and grading criteria for each security grading level, and to determine a grading matrix based on the security grading levels and the grading criteria. ,in, The number of safety classification levels;

[0244] Construction unit, used to construct the initial indicator evaluation matrix. In the hierarchical matrix Extract the first The row vectors corresponding to the key influencing factors, if the elements in the row vectors are in a decreasing order, then when hour, ,when hour, ,when hour, If the elements in the row vector are in an increasing order, then when hour, ,when hour, ,when hour, ,in, For the clustering dataset, the first The key influencing factors are in the first Data values ​​in each evaluation segment The first index in the initial index evaluation matrix Line number Column elements, The first in the hierarchical matrix Line number Column elements;

[0245] Matrix unit, used based on the influence weight With the initial index evaluation matrix Determine the final matrix :

[0246] ;

[0247] In the formula, For the final matrix, the first... Line number Column elements, Indicates the first The influence weights of each key influencing factor;

[0248] The evaluation output unit is used to determine the safety status evaluation function based on the final matrix. If the installation status evaluation function is satisfied, the final post-pipe jacking status is the [number missing]. There are several safety classification levels, where the safety status evaluation function is:

[0249] ;

[0250] In the formula, Represents the nth element in the final matrix row vectors. The evaluation threshold is used.

[0251] In other embodiments of the present invention, the present invention provides the following technical solution: a computer, including a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101, wherein the processor 101 executes the computer program to implement the post-construction status detection method of pipe jacking as described above.

[0252] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0253] The memory 102 may include a large-capacity memory for data or instructions. For example, and not limitingly, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 102 may include removable or non-removable (or fixed) media. Where appropriate, the memory 102 may be internal or external to a data processing device. In a particular embodiment, the memory 102 is non-volatile memory. In a particular embodiment, the memory 102 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random Access Memory (FPMDRAM), Extended Data Out Dynamic Random Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0254] The memory 102 can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101.

[0255] The processor 101 implements the above-mentioned post-pipe jacking status detection method by reading and executing computer program instructions stored in the memory 102.

[0256] In some embodiments, the computer may further include a communication interface 103 and a bus 100. For example, Figure 3 As shown, the processor 101, memory 102, and communication interface 103 are connected through bus 100 and complete communication with each other.

[0257] The communication interface 103 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of the present invention. The communication interface 103 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0258] Bus 100 includes hardware, software, or both, that couples components of a computer device together. Bus 100 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 100 may include one or more buses. Although specific buses are described and illustrated in the embodiments of the present invention, the present invention is contemplated by any suitable bus or interconnect.

[0259] The computer can execute the post-construction status detection method of the present invention based on the acquired post-construction status detection system for pipe jacking, thereby realizing post-construction status detection of pipe jacking.

[0260] In some other embodiments of the present invention, in conjunction with the above-described post-construction status detection method for pipe jacking, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-described post-construction status detection method for pipe jacking.

[0261] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0262] More specific examples of readable media (a non-exhaustive list) include: electrical connections (electronic devices) with one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0263] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0264] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0265] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for post-construction condition inspection of pipe jacking, characterized in that, include: Acquire post-construction status detection data of pipe jacking, and perform data preprocessing on the post-construction status detection data to obtain processed data; The analytic hierarchy process is used to identify key influencing factors, and a key dataset is extracted from the processed data based on these key influencing factors. The data in the key dataset are combined and denoised to obtain a denoised dataset; An improved clustering algorithm is used to cluster the denoised dataset to obtain a clustered dataset; Each of the key influencing factors is combined and weighted to obtain an influence weight, and the final post-construction state of the pipe jacking is determined based on the influence weight and the clustered dataset. The step of combining and denoising the data in the key dataset to obtain a denoised dataset includes: The data in the key dataset is decomposed to obtain several IMF components and trend terms. The several IMF components are then sorted in descending order to obtain the first IMF component set. Calculate the noise judgment value for each IMF component in the first IMF component set. : ； In the formula, This indicates the number of IMF components in the first IMF component set. Indicates the first IMF component set One IMF component; Determine the noise judgment value The target arrangement position of the IMF component corresponding to the minimum value is determined, and the IMF components before the target arrangement position are stored in the second IMF component set. The number of zero crossings of all IMF components in the first IMF component set is determined, and the IMF components with a number of zero crossings less than a preset number are stored in the third IMF component set. The remaining IMF components in the first IMF component set other than the second IMF component set and the third IMF component set are stored in the fourth IMF component set. The second IMF component set and the third IMF component set are respectively subjected to denoising and power transformation processing to obtain the first denoised IMF component set and the second denoised IMF component set. The denoised dataset is determined based on the first denoised IMF component set and the second denoised IMF component set. The step of performing denoising and power transformation processing on the second IMF component set and the third IMF component set respectively to obtain the first denoised IMF component set and the second denoised IMF component set, and determining the denoised dataset based on the first denoised IMF component set and the second denoised IMF component set includes: Wavelet threshold denoising is performed on the second IMF component set to obtain the first denoised IMF component set; Determine the power spectrum of the third IMF component set, and determine the power spectrum matrix based on the power spectrum; The power spectral matrix is ​​standardized to obtain a standard matrix. The eigenvectors of the standard matrix are extracted, and the principal component sequence is determined based on the eigenvectors and the standard matrix. : ； In the formula, For a standard matrix, For feature vectors; The principal components in the principal component sequence are sorted in descending order of contribution, and the first few principal components after descending order are extracted to obtain the target principal components. The reconstructed power spectrum is then determined based on the target principal components. : ； ； In the formula, Indicates the first One target principal component, express The corresponding feature vector, This represents the intermediate reconstructed power spectrum. They represent The Middle Line number Column elements, To reconstruct the adjustment factor, The power spectrum matrix is ​​the first... The mean of the column elements; For the reconstructed power spectrum Phase addition and inverse Fourier transform are performed to obtain the second denoised IMF component set. : ； In the formula, Represents the second denoised IMF component set The Middle One IMF component, This is the inverse Fourier transform. It is an imaginary number. Indicates the corresponding frequency phase; The first denoised IMF component set, the second denoised IMF component set, the fourth IMF component set, and the trend term are reconstructed to obtain a denoised dataset.

2. The method for post-construction condition detection of pipe jacking according to claim 1, characterized in that, The step of using an improved clustering algorithm to cluster the denoised dataset to obtain a clustered dataset includes: Determine the intermediate data points in the denoised dataset, and perform clustering using the intermediate data points as cluster centers to obtain the first cluster. If the number of data in the first cluster is less than the preset number, then the positive data in the denoised dataset is stored in the positive sample dataset and the negative data is stored in the negative sample dataset. Determine the first mean in the positive sample dataset and the second mean in the negative sample dataset, and calculate the absolute value of the difference between the first mean and the second mean; Clustering is performed based on the absolute value of the difference, and the clustered dataset is output.

3. The method for post-construction condition detection of pipe jacking according to claim 2, characterized in that, The step of clustering based on the absolute value of the difference and outputting the clustered dataset includes: If the absolute value of the difference is less than a preset value, then the data corresponding to the first mean or the second mean is used as the cluster center to perform clustering to obtain a second cluster. If the number of data points in the second cluster is less than a preset number, then any point is selected in the denoised dataset as a reference point. The data range is determined with the reference point as the center and a preset distance as the radius. If the number of data points within the data range is greater than a preset density threshold, then the reference point is used as a sample point. The center of the sample point is determined and clustering is performed with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised dataset is calculated. Data points with an Euclidean distance less than a preset distance are assigned to the class corresponding to the sample point to obtain the clustered dataset. If the absolute value of the difference is not less than a preset value, then the data corresponding to the first mean and the second mean are used as cluster centers to perform clustering to obtain the third cluster and the fourth cluster. If the number of data points in the third cluster is less than a preset number and the number of data points in the fourth cluster is less than a preset number, then any point in the denoised dataset is randomly selected as a reference point. The data range is determined with the reference point as the center and a preset distance as the radius. If the number of data points within the data range is greater than a preset density threshold, then the reference point is used as a sample point. The center of the sample point is determined and clustered with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised dataset is calculated. Data points with an Euclidean distance less than a preset distance are assigned to the class corresponding to the sample point to obtain the clustered dataset.

4. The method for post-construction condition detection of pipe jacking according to claim 1, characterized in that, The step of combining and weighting each of the key influencing factors to obtain influence weights, and determining the final post-construction state of the pipe jacking based on the influence weights and the clustered dataset includes: Select the least influential factor from the key influencing factors and calculate the least influential factor. First level of impact and other key influencing factors Second degree of influence : ； ； In the formula, For the evaluation section, For the first The key influencing factors are in the first The index values ​​in each evaluation segment The lowest impact factor in the first The index values ​​in each evaluation segment; Based on the first degree of influence and the second degree of influence Calculate the first weight : ； ； In the formula, Important values ​​for the indicator; Construct an original evaluation matrix, and determine the weight values ​​of the indicators based on the original evaluation matrix. : ； In the formula, The first in the original evaluation matrix Line number Column elements; Based on the weight value of the aforementioned indicators Determine the second weight : ； The first weight and the second weight are initially combined to obtain the combined weight. : ； In the formula, These represent the first and second combination parameters, respectively. These represent the weight sets composed of the first weight and the second weight, respectively; Determine the objective function: ； The objective function is solved to obtain the updated first combined parameters. Update the second combination parameters ; Based on the updated first combination parameters The updated second combination parameters Determine the influence weights : ； Construct an initial indicator evaluation matrix, and based on the initial indicator evaluation matrix and the influence weights Determine the final post-construction status of the pipe jacking project.

5. The method for post-construction condition detection of pipe jacking according to claim 4, characterized in that, The initial indicator evaluation matrix is ​​constructed, and the influence weights are used as the basis for this process. The steps to determine the final post-construction state of the pipe jacking project include: Determine the security classification levels and the classification criteria for each security classification level, and determine a classification matrix based on the security classification levels and the classification criteria. ,in, The number of safety classification levels; Constructing the initial indicator evaluation matrix In the hierarchical matrix Extract the first The row vectors corresponding to the key influencing factors, if the elements in the row vectors are in a decreasing order, then when hour, ,when hour, ,when hour, If the elements in the row vector are in an increasing order, then when hour, ,when hour, ,when hour, ,in, For the clustering dataset, the first The key influencing factors are in the first Data values ​​in each evaluation segment The first index in the initial index evaluation matrix Line number Column elements, The first in the hierarchical matrix Line number Column elements; Based on the influence weight With the initial index evaluation matrix Determine the final matrix : ； In the formula, For the final matrix, the first... Line number Column elements, Indicates the first The influence weights of each key influencing factor; Based on the final matrix, the safety status evaluation function is determined. If the installation status evaluation function is satisfied, then the final post-pipe jacking status is the [number missing]. There are several safety classification levels, where the safety status evaluation function is: ； In the formula, Represents the nth element in the final matrix row vectors. The evaluation threshold is used.

6. A post-construction status detection system for pipe jacking, wherein the system employs the post-construction status detection method as described in claim 1, characterized in that, The system includes: The preprocessing module is used to acquire post-construction status detection data of pipe jacking and to preprocess the post-construction status detection data of pipe jacking to obtain processed data. An extraction module is used to identify key influencing factors using the analytic hierarchy process, and to extract a key dataset from the processed data based on the key influencing factors. The denoising module is used to perform combined denoising processing on the data in the key dataset to obtain a denoised dataset; The clustering module is used to perform clustering processing on the denoised dataset using an improved clustering algorithm to obtain a clustered dataset; The status module is used to combine and assign weights to each of the key influencing factors to obtain influence weights, and to determine the final post-construction status of the pipe jacking based on the influence weights and the clustered dataset.

7. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the post-construction status detection method for pipe jacking as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the post-construction status detection method for pipe jacking as described in any one of claims 1 to 5.

Images